summaryrefslogtreecommitdiffstats
path: root/net/netfilter
diff options
context:
space:
mode:
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/Kconfig11
-rw-r--r--net/netfilter/core.c38
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c166
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c8
-rw-r--r--net/netfilter/ipvs/ip_vs_est.c5
-rw-r--r--net/netfilter/nf_conntrack_proto.c16
-rw-r--r--net/netfilter/nf_conntrack_proto_udp.c7
-rw-r--r--net/netfilter/nf_nat_core.c12
-rw-r--r--net/netfilter/nf_tables_core.c2
-rw-r--r--net/netfilter/nf_tables_trace.c4
-rw-r--r--net/netfilter/nfnetlink_hook.c16
-rw-r--r--net/netfilter/nft_chain_filter.c4
-rw-r--r--net/netfilter/nft_dynset.c11
-rw-r--r--net/netfilter/nft_meta.c8
-rw-r--r--net/netfilter/nft_payload.c60
-rw-r--r--net/netfilter/xt_RATEEST.c7
16 files changed, 207 insertions, 168 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 92a747896f80..3646fc195e7d 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -10,6 +10,17 @@ config NETFILTER_INGRESS
This allows you to classify packets from ingress using the Netfilter
infrastructure.
+config NETFILTER_EGRESS
+ bool "Netfilter egress support"
+ default y
+ select NET_EGRESS
+ help
+ This allows you to classify packets before transmission using the
+ Netfilter infrastructure.
+
+config NETFILTER_SKIP_EGRESS
+ def_bool NETFILTER_EGRESS && (NET_CLS_ACT || IFB)
+
config NETFILTER_NETLINK
tristate
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 63d032191e62..6dec9cd395f1 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -317,6 +317,12 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum,
return &dev->nf_hooks_ingress;
}
#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+ if (hooknum == NF_NETDEV_EGRESS) {
+ if (dev && dev_net(dev) == net)
+ return &dev->nf_hooks_egress;
+ }
+#endif
WARN_ON_ONCE(1);
return NULL;
}
@@ -335,7 +341,8 @@ static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg,
return 0;
}
-static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf)
+static inline bool __maybe_unused nf_ingress_hook(const struct nf_hook_ops *reg,
+ int pf)
{
if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) ||
(pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS))
@@ -344,6 +351,12 @@ static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf)
return false;
}
+static inline bool __maybe_unused nf_egress_hook(const struct nf_hook_ops *reg,
+ int pf)
+{
+ return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_EGRESS;
+}
+
static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf)
{
#ifdef CONFIG_JUMP_LABEL
@@ -383,9 +396,18 @@ static int __nf_register_net_hook(struct net *net, int pf,
switch (pf) {
case NFPROTO_NETDEV:
- err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS);
- if (err < 0)
- return err;
+#ifndef CONFIG_NETFILTER_INGRESS
+ if (reg->hooknum == NF_NETDEV_INGRESS)
+ return -EOPNOTSUPP;
+#endif
+#ifndef CONFIG_NETFILTER_EGRESS
+ if (reg->hooknum == NF_NETDEV_EGRESS)
+ return -EOPNOTSUPP;
+#endif
+ if ((reg->hooknum != NF_NETDEV_INGRESS &&
+ reg->hooknum != NF_NETDEV_EGRESS) ||
+ !reg->dev || dev_net(reg->dev) != net)
+ return -EINVAL;
break;
case NFPROTO_INET:
if (reg->hooknum != NF_INET_INGRESS)
@@ -418,6 +440,10 @@ static int __nf_register_net_hook(struct net *net, int pf,
if (nf_ingress_hook(reg, pf))
net_inc_ingress_queue();
#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+ if (nf_egress_hook(reg, pf))
+ net_inc_egress_queue();
+#endif
nf_static_key_inc(reg, pf);
BUG_ON(p == new_hooks);
@@ -475,6 +501,10 @@ static void __nf_unregister_net_hook(struct net *net, int pf,
if (nf_ingress_hook(reg, pf))
net_dec_ingress_queue();
#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+ if (nf_egress_hook(reg, pf))
+ net_dec_egress_queue();
+#endif
nf_static_key_dec(reg, pf);
} else {
WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 128690c512df..e93c937a8bf0 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1330,12 +1330,15 @@ drop:
* Check if outgoing packet belongs to the established ip_vs_conn.
*/
static unsigned int
-ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af)
+ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state)
{
+ struct netns_ipvs *ipvs = net_ipvs(state->net);
+ unsigned int hooknum = state->hook;
struct ip_vs_iphdr iph;
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
struct ip_vs_conn *cp;
+ int af = state->pf;
struct sock *sk;
EnterFunction(11);
@@ -1468,56 +1471,6 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
return NF_ACCEPT;
}
-/*
- * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain,
- * used only for VS/NAT.
- * Check if packet is reply for established ip_vs_conn.
- */
-static unsigned int
-ip_vs_reply4(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET);
-}
-
-/*
- * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT.
- * Check if packet is reply for established ip_vs_conn.
- */
-static unsigned int
-ip_vs_local_reply4(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET);
-}
-
-#ifdef CONFIG_IP_VS_IPV6
-
-/*
- * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain,
- * used only for VS/NAT.
- * Check if packet is reply for established ip_vs_conn.
- */
-static unsigned int
-ip_vs_reply6(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6);
-}
-
-/*
- * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT.
- * Check if packet is reply for established ip_vs_conn.
- */
-static unsigned int
-ip_vs_local_reply6(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6);
-}
-
-#endif
-
static unsigned int
ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb,
struct ip_vs_proto_data *pd,
@@ -1957,8 +1910,10 @@ out:
* and send it on its way...
*/
static unsigned int
-ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af)
+ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state)
{
+ struct netns_ipvs *ipvs = net_ipvs(state->net);
+ unsigned int hooknum = state->hook;
struct ip_vs_iphdr iph;
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
@@ -1966,6 +1921,7 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
int ret, pkts;
int conn_reuse_mode;
struct sock *sk;
+ int af = state->pf;
/* Already marked as IPVS request or reply? */
if (skb->ipvs_property)
@@ -2138,55 +2094,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
}
/*
- * AF_INET handler in NF_INET_LOCAL_IN chain
- * Schedule and forward packets from remote clients
- */
-static unsigned int
-ip_vs_remote_request4(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET);
-}
-
-/*
- * AF_INET handler in NF_INET_LOCAL_OUT chain
- * Schedule and forward packets from local clients
- */
-static unsigned int
-ip_vs_local_request4(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET);
-}
-
-#ifdef CONFIG_IP_VS_IPV6
-
-/*
- * AF_INET6 handler in NF_INET_LOCAL_IN chain
- * Schedule and forward packets from remote clients
- */
-static unsigned int
-ip_vs_remote_request6(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6);
-}
-
-/*
- * AF_INET6 handler in NF_INET_LOCAL_OUT chain
- * Schedule and forward packets from local clients
- */
-static unsigned int
-ip_vs_local_request6(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6);
-}
-
-#endif
-
-
-/*
* It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP
* related packets destined for 0.0.0.0/0.
* When fwmark-based virtual service is used, such as transparent
@@ -2199,45 +2106,36 @@ static unsigned int
ip_vs_forward_icmp(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
- int r;
struct netns_ipvs *ipvs = net_ipvs(state->net);
-
- if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
- return NF_ACCEPT;
+ int r;
/* ipvs enabled in this netns ? */
if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
return NF_ACCEPT;
- return ip_vs_in_icmp(ipvs, skb, &r, state->hook);
-}
-
+ if (state->pf == NFPROTO_IPV4) {
+ if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
+ return NF_ACCEPT;
#ifdef CONFIG_IP_VS_IPV6
-static unsigned int
-ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- int r;
- struct netns_ipvs *ipvs = net_ipvs(state->net);
- struct ip_vs_iphdr iphdr;
+ } else {
+ struct ip_vs_iphdr iphdr;
- ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr);
- if (iphdr.protocol != IPPROTO_ICMPV6)
- return NF_ACCEPT;
+ ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr);
- /* ipvs enabled in this netns ? */
- if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
- return NF_ACCEPT;
+ if (iphdr.protocol != IPPROTO_ICMPV6)
+ return NF_ACCEPT;
- return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr);
-}
+ return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr);
#endif
+ }
+ return ip_vs_in_icmp(ipvs, skb, &r, state->hook);
+}
static const struct nf_hook_ops ip_vs_ops4[] = {
/* After packet filtering, change source only for VS/NAT */
{
- .hook = ip_vs_reply4,
+ .hook = ip_vs_out_hook,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_NAT_SRC - 2,
@@ -2246,21 +2144,21 @@ static const struct nf_hook_ops ip_vs_ops4[] = {
* or VS/NAT(change destination), so that filtering rules can be
* applied to IPVS. */
{
- .hook = ip_vs_remote_request4,
+ .hook = ip_vs_in_hook,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_NAT_SRC - 1,
},
/* Before ip_vs_in, change source only for VS/NAT */
{
- .hook = ip_vs_local_reply4,
+ .hook = ip_vs_out_hook,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_NAT_DST + 1,
},
/* After mangle, schedule and forward local requests */
{
- .hook = ip_vs_local_request4,
+ .hook = ip_vs_in_hook,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_NAT_DST + 2,
@@ -2275,7 +2173,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = {
},
/* After packet filtering, change source only for VS/NAT */
{
- .hook = ip_vs_reply4,
+ .hook = ip_vs_out_hook,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_FORWARD,
.priority = 100,
@@ -2286,7 +2184,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = {
static const struct nf_hook_ops ip_vs_ops6[] = {
/* After packet filtering, change source only for VS/NAT */
{
- .hook = ip_vs_reply6,
+ .hook = ip_vs_out_hook,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP6_PRI_NAT_SRC - 2,
@@ -2295,21 +2193,21 @@ static const struct nf_hook_ops ip_vs_ops6[] = {
* or VS/NAT(change destination), so that filtering rules can be
* applied to IPVS. */
{
- .hook = ip_vs_remote_request6,
+ .hook = ip_vs_in_hook,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP6_PRI_NAT_SRC - 1,
},
/* Before ip_vs_in, change source only for VS/NAT */
{
- .hook = ip_vs_local_reply6,
+ .hook = ip_vs_out_hook,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP6_PRI_NAT_DST + 1,
},
/* After mangle, schedule and forward local requests */
{
- .hook = ip_vs_local_request6,
+ .hook = ip_vs_in_hook,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP6_PRI_NAT_DST + 2,
@@ -2317,14 +2215,14 @@ static const struct nf_hook_ops ip_vs_ops6[] = {
/* After packet filtering (but before ip_vs_out_icmp), catch icmp
* destined for 0.0.0.0/0, which is for incoming IPVS connections */
{
- .hook = ip_vs_forward_icmp_v6,
+ .hook = ip_vs_forward_icmp,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_FORWARD,
.priority = 99,
},
/* After packet filtering, change source only for VS/NAT */
{
- .hook = ip_vs_reply6,
+ .hook = ip_vs_out_hook,
.pf = NFPROTO_IPV6,
.hooknum = NF_INET_FORWARD,
.priority = 100,
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 6ea4b882435e..816f74dadfa3 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2016,6 +2016,12 @@ static struct ctl_table vs_vars[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "run_estimation",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
#ifdef CONFIG_IP_VS_DEBUG
{
.procname = "debug_level",
@@ -4089,6 +4095,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode;
tbl[idx++].data = &ipvs->sysctl_schedule_icmp;
tbl[idx++].data = &ipvs->sysctl_ignore_tunneled;
+ ipvs->sysctl_run_estimation = 1;
+ tbl[idx++].data = &ipvs->sysctl_run_estimation;
#ifdef CONFIG_IP_VS_DEBUG
/* Global sysctls must be ro in non-init netns */
if (!net_eq(net, &init_net))
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 05b8112ffb37..9a1a7af6a186 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -100,6 +100,9 @@ static void estimation_timer(struct timer_list *t)
u64 rate;
struct netns_ipvs *ipvs = from_timer(ipvs, t, est_timer);
+ if (!sysctl_run_estimation(ipvs))
+ goto skip;
+
spin_lock(&ipvs->est_lock);
list_for_each_entry(e, &ipvs->est_list, list) {
s = container_of(e, struct ip_vs_stats, est);
@@ -131,6 +134,8 @@ static void estimation_timer(struct timer_list *t)
spin_unlock(&s->lock);
}
spin_unlock(&ipvs->est_lock);
+
+skip:
mod_timer(&ipvs->est_timer, jiffies + 2*HZ);
}
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 8f7a9837349c..d1f2d3c8d2b1 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -155,6 +155,16 @@ unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff,
}
EXPORT_SYMBOL_GPL(nf_confirm);
+static bool in_vrf_postrouting(const struct nf_hook_state *state)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+ if (state->hook == NF_INET_POST_ROUTING &&
+ netif_is_l3_master(state->out))
+ return true;
+#endif
+ return false;
+}
+
static unsigned int ipv4_confirm(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
@@ -166,6 +176,9 @@ static unsigned int ipv4_confirm(void *priv,
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
return nf_conntrack_confirm(skb);
+ if (in_vrf_postrouting(state))
+ return NF_ACCEPT;
+
return nf_confirm(skb,
skb_network_offset(skb) + ip_hdrlen(skb),
ct, ctinfo);
@@ -374,6 +387,9 @@ static unsigned int ipv6_confirm(void *priv,
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
return nf_conntrack_confirm(skb);
+ if (in_vrf_postrouting(state))
+ return NF_ACCEPT;
+
protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
&frag_off);
if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index f8e3c0d2602f..3b516cffc779 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -104,10 +104,13 @@ int nf_conntrack_udp_packet(struct nf_conn *ct,
*/
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
unsigned long extra = timeouts[UDP_CT_UNREPLIED];
+ bool stream = false;
/* Still active after two seconds? Extend timeout. */
- if (time_after(jiffies, ct->proto.udp.stream_ts))
+ if (time_after(jiffies, ct->proto.udp.stream_ts)) {
extra = timeouts[UDP_CT_REPLIED];
+ stream = true;
+ }
nf_ct_refresh_acct(ct, ctinfo, skb, extra);
@@ -116,7 +119,7 @@ int nf_conntrack_udp_packet(struct nf_conn *ct,
return NF_ACCEPT;
/* Also, more likely to be important, and not a probe */
- if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
+ if (stream && !test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_ASSURED, ct);
} else {
nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 273117683922..4d50d51db796 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -699,6 +699,16 @@ unsigned int nf_nat_packet(struct nf_conn *ct,
}
EXPORT_SYMBOL_GPL(nf_nat_packet);
+static bool in_vrf_postrouting(const struct nf_hook_state *state)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+ if (state->hook == NF_INET_POST_ROUTING &&
+ netif_is_l3_master(state->out))
+ return true;
+#endif
+ return false;
+}
+
unsigned int
nf_nat_inet_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
@@ -715,7 +725,7 @@ nf_nat_inet_fn(void *priv, struct sk_buff *skb,
* packet filter it out, or implement conntrack/NAT for that
* protocol. 8) --RR
*/
- if (!ct)
+ if (!ct || in_vrf_postrouting(state))
return NF_ACCEPT;
nat = nfct_nat(ct);
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 866cfba04d6c..adc348056076 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -79,7 +79,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr,
if (priv->base == NFT_PAYLOAD_NETWORK_HEADER)
ptr = skb_network_header(skb);
else {
- if (!pkt->tprot_set)
+ if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
return false;
ptr = skb_network_header(skb) + nft_thoff(pkt);
}
diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c
index e4fe2f0780eb..84a7dea46efa 100644
--- a/net/netfilter/nf_tables_trace.c
+++ b/net/netfilter/nf_tables_trace.c
@@ -113,13 +113,13 @@ static int nf_trace_fill_pkt_info(struct sk_buff *nlskb,
int off = skb_network_offset(skb);
unsigned int len, nh_end;
- nh_end = pkt->tprot_set ? nft_thoff(pkt) : skb->len;
+ nh_end = pkt->flags & NFT_PKTINFO_L4PROTO ? nft_thoff(pkt) : skb->len;
len = min_t(unsigned int, nh_end - skb_network_offset(skb),
NFT_TRACETYPE_NETWORK_HSIZE);
if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len))
return -1;
- if (pkt->tprot_set) {
+ if (pkt->flags & NFT_PKTINFO_L4PROTO) {
len = min_t(unsigned int, skb->len - nft_thoff(pkt),
NFT_TRACETYPE_TRANSPORT_HSIZE);
if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb,
diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c
index f554e2ea32ee..d5c719c9e36c 100644
--- a/net/netfilter/nfnetlink_hook.c
+++ b/net/netfilter/nfnetlink_hook.c
@@ -185,7 +185,7 @@ static const struct nf_hook_entries *
nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev)
{
const struct nf_hook_entries *hook_head = NULL;
-#ifdef CONFIG_NETFILTER_INGRESS
+#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS)
struct net_device *netdev;
#endif
@@ -221,9 +221,9 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de
hook_head = rcu_dereference(net->nf.hooks_decnet[hook]);
break;
#endif
-#ifdef CONFIG_NETFILTER_INGRESS
+#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS)
case NFPROTO_NETDEV:
- if (hook != NF_NETDEV_INGRESS)
+ if (hook >= NF_NETDEV_NUMHOOKS)
return ERR_PTR(-EOPNOTSUPP);
if (!dev)
@@ -233,7 +233,15 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de
if (!netdev)
return ERR_PTR(-ENODEV);
- return rcu_dereference(netdev->nf_hooks_ingress);
+#ifdef CONFIG_NETFILTER_INGRESS
+ if (hook == NF_NETDEV_INGRESS)
+ return rcu_dereference(netdev->nf_hooks_ingress);
+#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+ if (hook == NF_NETDEV_EGRESS)
+ return rcu_dereference(netdev->nf_hooks_egress);
+#endif
+ fallthrough;
#endif
default:
return ERR_PTR(-EPROTONOSUPPORT);
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 3ced0eb6b7c3..c3563f0be269 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -310,9 +310,11 @@ static const struct nft_chain_type nft_chain_filter_netdev = {
.name = "filter",
.type = NFT_CHAIN_T_DEFAULT,
.family = NFPROTO_NETDEV,
- .hook_mask = (1 << NF_NETDEV_INGRESS),
+ .hook_mask = (1 << NF_NETDEV_INGRESS) |
+ (1 << NF_NETDEV_EGRESS),
.hooks = {
[NF_NETDEV_INGRESS] = nft_do_chain_netdev,
+ [NF_NETDEV_EGRESS] = nft_do_chain_netdev,
},
};
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 6ba3256fa844..87f3af4645d9 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -198,17 +198,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
return -EBUSY;
priv->op = ntohl(nla_get_be32(tb[NFTA_DYNSET_OP]));
- switch (priv->op) {
- case NFT_DYNSET_OP_ADD:
- case NFT_DYNSET_OP_DELETE:
- break;
- case NFT_DYNSET_OP_UPDATE:
- if (!(set->flags & NFT_SET_TIMEOUT))
- return -EOPNOTSUPP;
- break;
- default:
+ if (priv->op > NFT_DYNSET_OP_DELETE)
return -EOPNOTSUPP;
- }
timeout = 0;
if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index a7e01e9952f1..fe91ff5f8fbe 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -244,7 +244,11 @@ static bool nft_meta_get_eval_ifname(enum nft_meta_keys key, u32 *dest,
case NFT_META_OIF:
nft_meta_store_ifindex(dest, nft_out(pkt));
break;
- case NFT_META_IIFTYPE:
+ case NFT_META_IFTYPE:
+ if (!nft_meta_store_iftype(dest, pkt->skb->dev))
+ return false;
+ break;
+ case __NFT_META_IIFTYPE:
if (!nft_meta_store_iftype(dest, nft_in(pkt)))
return false;
break;
@@ -329,7 +333,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
nft_reg_store8(dest, nft_pf(pkt));
break;
case NFT_META_L4PROTO:
- if (!pkt->tprot_set)
+ if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
goto err;
nft_reg_store8(dest, pkt->tprot);
break;
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index a44b14f6c0dc..cbfe4e4a4ad7 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -22,6 +22,7 @@
#include <linux/icmpv6.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/ip.h>
#include <net/sctp/checksum.h>
static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off,
@@ -79,6 +80,45 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len)
return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0;
}
+static int __nft_payload_inner_offset(struct nft_pktinfo *pkt)
+{
+ unsigned int thoff = nft_thoff(pkt);
+
+ if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
+ return -1;
+
+ switch (pkt->tprot) {
+ case IPPROTO_UDP:
+ pkt->inneroff = thoff + sizeof(struct udphdr);
+ break;
+ case IPPROTO_TCP: {
+ struct tcphdr *th, _tcph;
+
+ th = skb_header_pointer(pkt->skb, thoff, sizeof(_tcph), &_tcph);
+ if (!th)
+ return -1;
+
+ pkt->inneroff = thoff + __tcp_hdrlen(th);
+ }
+ break;
+ default:
+ return -1;
+ }
+
+ pkt->flags |= NFT_PKTINFO_INNER;
+
+ return 0;
+}
+
+static int nft_payload_inner_offset(const struct nft_pktinfo *pkt)
+{
+ if (!(pkt->flags & NFT_PKTINFO_INNER) &&
+ __nft_payload_inner_offset((struct nft_pktinfo *)pkt) < 0)
+ return -1;
+
+ return pkt->inneroff;
+}
+
void nft_payload_eval(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
@@ -108,10 +148,15 @@ void nft_payload_eval(const struct nft_expr *expr,
offset = skb_network_offset(skb);
break;
case NFT_PAYLOAD_TRANSPORT_HEADER:
- if (!pkt->tprot_set)
+ if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
goto err;
offset = nft_thoff(pkt);
break;
+ case NFT_PAYLOAD_INNER_HEADER:
+ offset = nft_payload_inner_offset(pkt);
+ if (offset < 0)
+ goto err;
+ break;
default:
BUG();
}
@@ -610,10 +655,15 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
offset = skb_network_offset(skb);
break;
case NFT_PAYLOAD_TRANSPORT_HEADER:
- if (!pkt->tprot_set)
+ if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
goto err;
offset = nft_thoff(pkt);
break;
+ case NFT_PAYLOAD_INNER_HEADER:
+ offset = nft_payload_inner_offset(pkt);
+ if (offset < 0)
+ goto err;
+ break;
default:
BUG();
}
@@ -622,7 +672,8 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
offset += priv->offset;
if ((priv->csum_type == NFT_PAYLOAD_CSUM_INET || priv->csum_flags) &&
- (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER ||
+ ((priv->base != NFT_PAYLOAD_TRANSPORT_HEADER &&
+ priv->base != NFT_PAYLOAD_INNER_HEADER) ||
skb->ip_summed != CHECKSUM_PARTIAL)) {
fsum = skb_checksum(skb, offset, priv->len, 0);
tsum = csum_partial(src, priv->len, 0);
@@ -741,6 +792,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
case NFT_PAYLOAD_LL_HEADER:
case NFT_PAYLOAD_NETWORK_HEADER:
case NFT_PAYLOAD_TRANSPORT_HEADER:
+ case NFT_PAYLOAD_INNER_HEADER:
break;
default:
return ERR_PTR(-EOPNOTSUPP);
@@ -759,7 +811,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
- base != NFT_PAYLOAD_LL_HEADER)
+ base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER)
return &nft_payload_fast_ops;
else
return &nft_payload_ops;
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 0d5c422f8745..8aec1b529364 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -94,11 +94,11 @@ static unsigned int
xt_rateest_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_rateest_target_info *info = par->targinfo;
- struct gnet_stats_basic_packed *stats = &info->est->bstats;
+ struct gnet_stats_basic_sync *stats = &info->est->bstats;
spin_lock_bh(&info->est->lock);
- stats->bytes += skb->len;
- stats->packets++;
+ u64_stats_add(&stats->bytes, skb->len);
+ u64_stats_inc(&stats->packets);
spin_unlock_bh(&info->est->lock);
return XT_CONTINUE;
@@ -143,6 +143,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
if (!est)
goto err1;
+ gnet_stats_basic_sync_init(&est->bstats);
strlcpy(est->name, info->name, sizeof(est->name));
spin_lock_init(&est->lock);
est->refcnt = 1;